Computer Graphics
TU Braunschweig

NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting


NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting

3D Gaussian Splatting can exploit frustum culling and level- of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling.

We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer.

Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques.


Author(s): Brent Zoomers, Florian Hahlbohm, Joni Vanherck, Lode Jorissen, Marcus Magnor, Nick Michiels
Published: to appear
Type: Article in conference proceedings
Book: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Presented at: Conference on Computer Vision and Pattern Recognition (CVPR) 2026
Project(s): Real-Action VR 

BibTex Webpage arXiv 



@inproceedings{zoomers2026nvgs,
  title = {{NVGS}: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting},
  author = {Zoomers, Brent and Hahlbohm, Florian and Vanherck, Joni and Jorissen, Lode and Magnor, Marcus and Michiels, Nick},
  booktitle = {{IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})},
  year = {2026}
}

Authors